We are seeking a skilled
GenAI & Agentic AI Engineer
with strong experience in building end‑to‑end AI/ML solutions, Generative AI applications, and agent‑based automation workflows. The ideal candidate will have a solid background in machine learning along with hands‑on expertise in LLMs, RAG, embeddings, vector databases, and Agentic AI frameworks such as CrewAI, AutoGen, LangGraph, or LangChain Agents.
Key Responsibilities
Build and deploy
GenAI applications
using LLMs (OpenAI, Azure OpenAI, Claude, Gemini, Llama, etc.).
Develop
Agentic AI workflows
using frameworks such as
CrewAI, AutoGen, LangGraph, or LangChain Agents .
Design and implement
RAG pipelines , vector search solutions, and embedding‑based retrieval systems.
Build scalable AI services using
Python , FastAPI/Flask, and cloud platforms (Azure/AWS/GCP).
Collaborate with cross‑functional teams to define use cases and convert them into production‑ready GenAI solutions.
Implement
hallucination reduction , prompt‑engineering strategies, and model evaluation methods.
Integrate LLMs with enterprise applications, APIs, and automation workflows.
Work with vector databases (FAISS, Pinecone, Chroma, Weaviate) for semantic search.
Monitor, evaluate, and optimize GenAI models for accuracy, performance, and cost.
Required Skills & Experience
5+ years of experience in AI/ML, including model development, data preprocessing, EDA, training, and evaluation.
2+ years of hands‑on experience in Generative AI (LLMs, embeddings, RAG, LLM‑based apps).
6+ months of hands‑on experience with Agentic AI frameworks (CrewAI / AutoGen / LangGraph / LangChain Agents).
Strong proficiency in
Python
and ML libraries (Scikit‑learn, Pandas, NumPy).
Experience with
OpenAI APIs , Azure OpenAI, HuggingFace, and prompt engineering.
Familiarity with building scalable APIs using
FastAPI , Flask, or Django.
Hands‑on knowledge of cloud services (Azure/AWS/GCP) for AI deployment.
Strong understanding of REST APIs, microservices, and integration patterns.
Experience with Git, CI/CD, Docker, and model deployment best practices.